Agent Skills

All skills

domain-modeling (mattpocock/skills) vs verification-before-completion (obra/superpowers)

domain-modeling (mattpocock/skills)

28.2 / 30

RecommendedSafe

domain-modeling: turns plain 'set up a glossary / record this decision' requests into the short GLOSSARY.md + ADR format (control 2.8, skill 5.0), a one-sentence prompt gets 4.6; no token overhead

  • SOTAPass

verification-before-completion (obra/superpowers)

25.0 / 30

SituationalSafe

verification-before-completion: all 18 runs verify before claiming done, with or without the skill (5.0 / 5.0 / 5.0); the skill adds ~20% tokens

  • SOTAPass